metadata

license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_deit_tiny_sgd_0001_fold3
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.59

smids_1x_deit_tiny_sgd_0001_fold3

This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.9030
Accuracy: 0.59

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2891	1.0	75	1.2964	0.35
1.1841	2.0	150	1.2323	0.3683
1.1375	3.0	225	1.1862	0.3917
1.1786	4.0	300	1.1551	0.3933
1.0678	5.0	375	1.1335	0.3867
1.1099	6.0	450	1.1171	0.41
1.0735	7.0	525	1.1035	0.43
1.0557	8.0	600	1.0918	0.4283
1.0742	9.0	675	1.0815	0.435
1.0667	10.0	750	1.0716	0.45
1.0307	11.0	825	1.0624	0.465
1.0285	12.0	900	1.0538	0.48
1.0155	13.0	975	1.0454	0.4883
1.0004	14.0	1050	1.0371	0.4983
0.9896	15.0	1125	1.0296	0.5
0.9962	16.0	1200	1.0219	0.5033
0.9993	17.0	1275	1.0142	0.51
0.982	18.0	1350	1.0069	0.5067
0.9813	19.0	1425	0.9999	0.51
0.9516	20.0	1500	0.9928	0.5183
0.9735	21.0	1575	0.9864	0.53
0.9641	22.0	1650	0.9800	0.5367
0.9696	23.0	1725	0.9741	0.5417
0.9132	24.0	1800	0.9683	0.55
0.9427	25.0	1875	0.9629	0.55
0.956	26.0	1950	0.9577	0.5483
0.9026	27.0	2025	0.9527	0.5517
0.9342	28.0	2100	0.9481	0.5517
0.9171	29.0	2175	0.9437	0.5517
0.9183	30.0	2250	0.9395	0.5517
0.9037	31.0	2325	0.9358	0.555
0.8583	32.0	2400	0.9322	0.555
0.8838	33.0	2475	0.9289	0.5567
0.9061	34.0	2550	0.9258	0.56
0.877	35.0	2625	0.9229	0.5667
0.8993	36.0	2700	0.9203	0.57
0.8879	37.0	2775	0.9178	0.575
0.9187	38.0	2850	0.9156	0.5767
0.8776	39.0	2925	0.9136	0.5817
0.8807	40.0	3000	0.9117	0.5833
0.9149	41.0	3075	0.9100	0.5867
0.9426	42.0	3150	0.9085	0.5867
0.9085	43.0	3225	0.9072	0.5883
0.8614	44.0	3300	0.9060	0.5883
0.9002	45.0	3375	0.9051	0.59
0.8489	46.0	3450	0.9043	0.59
0.8489	47.0	3525	0.9037	0.59
0.8906	48.0	3600	0.9033	0.59
0.8819	49.0	3675	0.9031	0.59
0.8423	50.0	3750	0.9030	0.59

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0